Overcoming data scarcity in life-threatening arrhythmia detection through transfer learning

Abstract Background Life-threatening arrhythmias (LTAs) are a leading cause of death worldwide. Enhancing LTA detection in wearable monitoring systems is of great importance. One of the main challenges in building robust LTA detection algorithms is the limited availability of labeled LTA data. Metho...

Full description

Saved in:
Bibliographic Details
Main Authors: Giuliana Monachino, Beatrice Zanchi, Michael Wand, Giulio Conte, Athina Tzovara, Francesca Dalia Faraci
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Communications Medicine
Online Access:https://doi.org/10.1038/s43856-025-00982-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238458041630720
author Giuliana Monachino
Beatrice Zanchi
Michael Wand
Giulio Conte
Athina Tzovara
Francesca Dalia Faraci
author_facet Giuliana Monachino
Beatrice Zanchi
Michael Wand
Giulio Conte
Athina Tzovara
Francesca Dalia Faraci
author_sort Giuliana Monachino
collection DOAJ
description Abstract Background Life-threatening arrhythmias (LTAs) are a leading cause of death worldwide. Enhancing LTA detection in wearable monitoring systems is of great importance. One of the main challenges in building robust LTA detection algorithms is the limited availability of labeled LTA data. Methods We introduce an effective deep-learning algorithm for detecting LTAs from single-lead ECGs in out-of-hospital cardiac arrest applications. We address the data-scarcity issue by applying a transfer learning approach. The deep-learning model is pre-trained on a massive dataset (72’952 recordings) for rhythm classification and then fine-tuned on the target dataset with LTA events (102 recordings). Results Our model achieves a sensitivity of 92.68% and a specificity of 99.48%, with a granularity of 1.28 seconds, in detecting LTAs. Additionally, a confidence estimation procedure is introduced to enable emergency service pre-alerts in case of low-confidence detections. Conclusions Our transfer learning based approach has the potential to significantly mitigate the impact of data scarcity, advancing LTA detection in wearable monitoring systems, and supporting rapid, life-saving interventions in out-of-hospital cardiac arrest emergencies.
format Article
id doaj-art-49e7e85b85714aa6a88a543c2ab2da6c
institution Kabale University
issn 2730-664X
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Communications Medicine
spelling doaj-art-49e7e85b85714aa6a88a543c2ab2da6c2025-08-20T04:01:36ZengNature PortfolioCommunications Medicine2730-664X2025-07-015111010.1038/s43856-025-00982-9Overcoming data scarcity in life-threatening arrhythmia detection through transfer learningGiuliana Monachino0Beatrice Zanchi1Michael Wand2Giulio Conte3Athina Tzovara4Francesca Dalia Faraci5Institute of Digital Technologies for Personalized Healthcare - MeDiTech, Department of Innovative Technologies, University of Applied Sciences and Arts of Southern SwitzerlandInstitute of Digital Technologies for Personalized Healthcare - MeDiTech, Department of Innovative Technologies, University of Applied Sciences and Arts of Southern SwitzerlandInstitute of Digital Technologies for Personalized Healthcare - MeDiTech, Department of Innovative Technologies, University of Applied Sciences and Arts of Southern SwitzerlandCardiology Department, Cardiocentro Ticino Institute, Ente Ospedaliero CantonaleInstitute of Informatics, University of BernInstitute of Digital Technologies for Personalized Healthcare - MeDiTech, Department of Innovative Technologies, University of Applied Sciences and Arts of Southern SwitzerlandAbstract Background Life-threatening arrhythmias (LTAs) are a leading cause of death worldwide. Enhancing LTA detection in wearable monitoring systems is of great importance. One of the main challenges in building robust LTA detection algorithms is the limited availability of labeled LTA data. Methods We introduce an effective deep-learning algorithm for detecting LTAs from single-lead ECGs in out-of-hospital cardiac arrest applications. We address the data-scarcity issue by applying a transfer learning approach. The deep-learning model is pre-trained on a massive dataset (72’952 recordings) for rhythm classification and then fine-tuned on the target dataset with LTA events (102 recordings). Results Our model achieves a sensitivity of 92.68% and a specificity of 99.48%, with a granularity of 1.28 seconds, in detecting LTAs. Additionally, a confidence estimation procedure is introduced to enable emergency service pre-alerts in case of low-confidence detections. Conclusions Our transfer learning based approach has the potential to significantly mitigate the impact of data scarcity, advancing LTA detection in wearable monitoring systems, and supporting rapid, life-saving interventions in out-of-hospital cardiac arrest emergencies.https://doi.org/10.1038/s43856-025-00982-9
spellingShingle Giuliana Monachino
Beatrice Zanchi
Michael Wand
Giulio Conte
Athina Tzovara
Francesca Dalia Faraci
Overcoming data scarcity in life-threatening arrhythmia detection through transfer learning
Communications Medicine
title Overcoming data scarcity in life-threatening arrhythmia detection through transfer learning
title_full Overcoming data scarcity in life-threatening arrhythmia detection through transfer learning
title_fullStr Overcoming data scarcity in life-threatening arrhythmia detection through transfer learning
title_full_unstemmed Overcoming data scarcity in life-threatening arrhythmia detection through transfer learning
title_short Overcoming data scarcity in life-threatening arrhythmia detection through transfer learning
title_sort overcoming data scarcity in life threatening arrhythmia detection through transfer learning
url https://doi.org/10.1038/s43856-025-00982-9
work_keys_str_mv AT giulianamonachino overcomingdatascarcityinlifethreateningarrhythmiadetectionthroughtransferlearning
AT beatricezanchi overcomingdatascarcityinlifethreateningarrhythmiadetectionthroughtransferlearning
AT michaelwand overcomingdatascarcityinlifethreateningarrhythmiadetectionthroughtransferlearning
AT giulioconte overcomingdatascarcityinlifethreateningarrhythmiadetectionthroughtransferlearning
AT athinatzovara overcomingdatascarcityinlifethreateningarrhythmiadetectionthroughtransferlearning
AT francescadaliafaraci overcomingdatascarcityinlifethreateningarrhythmiadetectionthroughtransferlearning